A speaker recognition algorithm based on factor analysis

Speech applications, which operate a system by voice commands, facilitate web access for disabled and visually impaired users. Human-computer interactions, such as speaking and listening to web applications, provide options for developing a multimodal interaction tool in the accessible design of an intelligent web. Speaker identification and verification are essential functionalities for intelligent web programs with speech applications. This paper proposes an enhanced Gaussian mixture model (GMM) method by incorporating the information derived from the support vector machine (SVM), called EGMM-SVM, for web-based applications with speaker recognition. The EGMM-SVM improves the accuracy of the estimated likelihood scores between the speech frame and the GMM. In EGMM-SVM, SVM plays a crucial role in transmitting the quality information of the utterances from a test speaker, through the GMM when performing GMM likelihood calculations. The experimental results show that speaker recognition by using the developed EGMM-SVM with an accurate operation mechanism for Gaussian distribution derivations yields a higher recognition rate than does a conventional GMM without any considerations on the quality of test speech utterances.

This paper presents an automatic speaker state recognition approach which models the factor vectors in the latent factor analysis framework improving upon the Gaussian Mixture Model (GMM) baseline performance. We investigate both intoxicated and affective speaker states. We consider the affective speech signal as the original normal average speech signal being corrupted by the affective channel effects. Rather than reducing the channel variability to enhance the robustness as in the speaker verification task, we directly model the speaker state on the channel factors under the factor analysis framework. In this work, the speaker state factor vectors are extracted and modeled by the latent factor analysis approach in the GMM modeling framework and support vector machine classification method. Experimental results show that the proposed speaker state factor vector modeling system achieved 5.34% and 1.49% unweighted accuracy improvement over the GMM baseline on the intoxicated speech detection task (Alcohol Language Corpus) and the emotion recognition task (IEMOCAP database), respectively.

This paper presents a comparison between several features normalization methods, and a comparison between different types of Gaussian Mixture Model (GMM) based supervectors normalizations for robust Speaker Verification. We implemented the methods of normalizations as a part of speaker verification system using Support Vector Machine (SVM) classifier and GMM-based supervectors. When implementing the speaker recognition system, we used Mel Frequency Cepstral Coefficients (MFCC) feature extraction. A valid question is which features normalization to use, if any. We examine the most common methods of feature normalizations, such as: Feature Warping mapping, and Cepstral Mean Subtraction (CMS) normalization with and without variance normalization. These methods were compared to features without normalization at all, and to a basic [-1, 1] normalization. In addition, we applied few types of normalizations to the GMM-mean supervectors, in order to improve the performance of the SVM classifier. All comparisons of the speaker verification system had been done in terms of DET curve, EER (Equal Error Rate) and Min. DCF. The best results we achieved were on combined supervector normalizations of Universal Background Model (UBM) Standard Deviation (STD) and [-1, 1] normalization. The type of the MFCC normalization has no big influence on the verification performance. The best results were: EER about 5.0% and MIN. DCF of 0.02.

Logistic regression is a well known classification method in the field of statistical learning. Recently, a kernelized version of logistic regression has become very popular, because it allows non-linear probabilistic classification and shows promising results on several benchmark problems. In this paper we show that kernel logistic regression (KLR) and especially its sparse extensions (SKLR) are useful alternatives to standard Gaussian mixture models (GMMs) and support vector machines (SVMs) in Speaker recognition. While the classification results of KLR and SKLR are similar to the results of SVMs, we show that SKLR produces highly sparse models. Unlike SVMs the kernel logistic regression also provides an estimate of the conditional probability of class membership. In speaker identification experiments the SKLR methods outperform the SVM and the GMM baseline system on the POLY-COST database

In the biometrics community, face and speaker recognition are mature fields in which several systems have been proposed over the past twenty years. While existing systems perform well under controlled recording conditions, mismatch caused by the use of different sensors or a lack of cooperation from the subject still significantly affects performance, especially in challenging scenarios such as in forensics. Furthermore, existing methods suffer from scalability issues, which prevents them from taking advantage of increasingly large amounts of training data. This is otherwise a promising approach to improve accuracy in such challenging scenarios. In this thesis we address these problems of mismatch and complexity by developing scalable probabilistic models that we apply to face, speaker and bimodal recognition. Our contributions are four-fold. First, we propose a unified framework for session variability modeling techniques based on Gaussian mixture models (GMM), that encompasses inter-session variability (ISV) modeling, joint factor analysis (JFA) and total variability (TV) modeling. Second, we propose a novel exact and scalable formulation of probabilistic linear discriminant analysis (PLDA), which is a probabilistic and generative framework that models between-class and within-class variations. This formulation solves a major scalability issue, by improving both the time complexity of the training procedure from cubic to linear with respect to the number of samples per class, and the complexity of the scoring procedure. Furthermore, the implementations of all the proposed techniques are integrated into a novel collaborative open source software library called Bob 1 that enforces fair evaluations and encourages reproducible research. Fourth and finally, large-scale experiments are conducted with all of the above machine learning algorithms on several databases such as FRGC for face recognition, NIST SRE12 for speaker recognition and MOBIO for bimodal recognition, showing competitive performances.

We put forward a new SVM-GMM mixture model to improve recognition rate of the speaker verification system in the paper. Support vector machines (SVM) and Gaussian mixture model (GMM) are widely applied to the speaker verification, but both have some disadvantages. We present a new approach for speaker verification based on their feature. The new model introduce the output of the Gaussian mixture model to Support vector machines, in order to adjust the probabilistic output of the support vector of machines. It can compliment support vector machines with probabilistic information. The experiments have proved that SVM-GMM mixture model can effective enhance the recognition rate of the speaker verification system.

Advances in SVM-Based System Using GMM Super Vectors for Text-Independent Speaker Verification

Applying SVMs and weight-based factor analysis to unsupervised adaptation for speaker verification

Relevance factor of maximum a posteriori adaptation for GMM–NAP–SVM in speaker and language recognition

Gaussian Mixture models is one of the most popular statistical methods in speaker recognition. The purpose of this research is to perform experiments of speaker recognition using various feature vectors: four formants, four formants with fundamental frequency and mel cepstrum coefficients. Gaussian mixture models using mel cepstrum coefficients is baseline in speaker recognition and gives one of the best results in text independent speaker recognition. After implementing experiments of speaker recognition and comparing experimental results we can affirm that mel scale cepstral coefficients and four formants with fundamental frequency gives quite the same recognition accuracy, but creating of Gaussian mixture speaker models and recognition process continues a few times longer using mel scale cepstral coefficients, because count of calculations is few times greater in that case. Using only four formants gives the worst results of recognition accuracy. Ill. 7, bibl. 12 (in English; summaries in English, Russian and Lithuanian).

This paper presents a text-independent speaker verification system using support vector machines (SVMs) with score-space kernels. Score-space kernels generalize Fisher kernels and are based on underlying generative models such as Gaussian mixture models (GMMs). This approach provides direct discrimination between whole sequences, in contrast with the frame-level approaches at the heart of most current systems. The resultant SVMs have a very high dimensionality since it is related to the number of parameters in the underlying generative model. To address problems that arise in the resultant optimization we introduce a technique called spherical normalization that preconditions the Hessian matrix. We have performed speaker verification experiments using the PolyVar database. The SVM system presented here reduces the relative error rates by 34% compared to a GMM likelihood ratio system.

Speaker recognition is carried out in the space of the functional parameters of the area of the glottal cross-section, found by solving the inverse problem. This problem is solved in two stages: first, the signal obtained by inverse filtering is approximated using the vocal source model, and then the glottal area model parameters, which generate the calculated vocal source impulse, are computed. Speaker recognition is carried out on a database of Russian numerals from 0 to 9 separately for men (48 speakers) and women (37 speakers) at the segments of stressed vowels. Various methods of recognition are studied: the Gaussian mixture model (GMM), support vector machines (SVMs), discriminant analysis, naive Bayes classifier (NB), the method of classification trees (CTREE), and the Parzen window classifier. The best results were obtained using the method of SVMs and the Parzen method: the average total error of identification of men was 4.9% and 5.1%, and that of women--8.2% and 8.8%, respectively.

Speech signals carry various bits of information relevant to the speaker such as age, gender, accent, language, health, and emotions. Emotions are conveyed through modulations of facial and vocal expressions. This paper conducts an empirical comparison of performances between the classical classifiers: Gaussian Mixture Model (GMM), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial neural networks (ANN); and the deep learning classifiers, i.e., Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU) in addition to the ivector approach for a text-independent speaker verification task in neutral and emotional talking environments. The deep models undergo hyperparameter tuning using the Grid Search optimization algorithm. The models are trained and tested using a private Arabic Emirati Speech Database, Ryerson Audio–Visual Database of Emotional Speech and Song dataset (RAVDESS) database, and a public Crowd-Sourced Emotional Multimodal Actors (CREMA) database. Experimental results illustrate that deep architectures do not necessarily outperform classical classifiers. In fact, evaluation was carried out through Equal Error Rate (EER) along with Area Under the Curve (AUC) scores. The findings reveal that the GMM model yields the lowest EER values and the best AUC scores across all datasets, amongst classical classifiers. In addition, the ivector model surpasses all the fine-tuned deep models (CNN, LSTM, and GRU) based on both evaluation metrics in the neutral, as well as the emotional speech. In addition, the GMM outperforms the ivector using the Emirati and RAVDESS databases.

In recent times, there have been increased rates at which researchers are searching for advanced ways of carrying out land-use land-cover (LULC) mapping, especially in developing countries. Four machine-learning algorithms, namely Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbour (K-NN), and Gaussian Mixture Models (GMM) were examined. This study also attempted to validate the various models using the index-based validation method. Accuracy assessment was performed by using the Kappa coefficient. The results of the LULC showed that RF classified 23% of the study area as bare land, SVM has 24% of the study area classified as bare land, K-NN also allotted 24% to bare land, while that of GMM classifier was 30%. The overall accuracy of RF, SVM, K-NN and GMM were 0.9840, 0.9780, 0.9641 and 0.9421 respectively. The Kappa Coefficient of the various classifiers were RF (0.9695), SVM (0.9580), K-NN (0.9319) and GMM (0.8916). This study showed that though all the algorithms performed relatively very well, RF performed better than the other classifiers. It suffices to state that, there is a need for further studies since other extraneous environmental variables may be underpinning these conclusions.

This paper proposes a new approach for text-independent speaker recognition using twin support vector machines (TWSVMs) and feature extraction based on Gaussian mixture models (GMMs). Because of the perfect discriminability and the ability of managing large scale dataset, the proposed approach performs better than the traditional support vector machines (SVMs) on Ahumada Biometric Database and Gaudi Biometric Database.